Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1187573 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1052. Min Act: -0.0002

Data Index: 983683 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1020. Min Act: -0.0002

Data Index: 481196 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0911. Min Act: -0.0002

Data Index: 117329 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0956. Min Act: -0.0002

Data Index: 785004 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0907. Min Act: -0.0002

Data Index: 684215 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0984. Min Act: -0.0002

Data Index: 731248 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1070304 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0911. Min Act: -0.0002

Data Index: 784459 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0902. Min Act: -0.0002

Data Index: 738893 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1013557 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1205080 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0846. Min Act: -0.0002

Data Index: 710775 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0811. Min Act: -0.0002

Data Index: 703238 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0785. Min Act: -0.0002

Data Index: 360985 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0773. Min Act: -0.0002

Data Index: 360516 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0862. Min Act: -0.0002

Data Index: 120151 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1126233 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1009109 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0762. Min Act: -0.0002

Data Index: 96476 (C4 (Web Text))

Max Activating Token Index: 779